Effortlessly Build, Run, Secure, and Manage Traffic for a Generative AI Application From...
summary
A runnable GenAI demo is built: a Streamlit web app that chats with local LLaMA models (Nama 3.2 and Nava for images) and uses RAG with ChromaDB; it deploys to a kind Kubernetes cluster with Flannel CNI, Istio/ambient mesh identity via SPIFFE, and is delivered by Argo CD to Kubernetes Gateway API routes. Kiali and Prometheus provide observability. A K‑agent AI reliability agent finds a mismatched HTTPRoute port, the port is fixed, and the app then serves chat and image mood analysis successfully.
AI-written summary · about
chapters (5)
- 0:00Building a generative AI app
- 4:18Kubernetes demo setup
- 14:15Ingress gateway for traffic
- 18:32AI reliability troubleshooting
- 33:39Demo recap and Q&A
related talks
31mUnlock the Full Potential of Generative AI via Microservices and Istio Service Mesh
31mBuilding and Orchestrating Real Production-ready Agentic AI Systems
25mSecuring AI Pipelines: Real-World Attacks on Kubernetes-Based AI Infrastructure
41mFrom RAGs to riches: Build an AI document interrogation app in 30 mins
09mTransform Your Kubernetes Cluster Into a GenAI Platform: Get Ready-t...
40mRolling out Enterprise AI: Tools, Insights, & Team Empowerment
02h 35mBringing GenAI to the Modern Enterprise. A production use-case. In Serverless Java!
34mBuilding Multi-Agent Generative-AI Applications with AutoGen